Vehicle with external audio speaker and microphone

Abstract

Various systems and methods for implementing a vehicle with an external speaker and microphone are described herein. A system includes an audio processor to receive audio data, the audio data sensed by a microphone array installed on the vehicle, the audio data generated by a source outside of the vehicle; an audio classification circuit to analyze the audio data using a machine learning technique to determine a sound event; and a vehicle interface to transmit a message to a vehicle control system, the message based on the sound event.

What is claimed is: 
     
       1. A system for audio events detection in a vehicle, the system comprising:
 an audio processor to receive audio data, the audio data sensed by a microphone array installed on the vehicle; 
 a camera installed on the vehicle; 
 a speaker installed on the vehicle; 
 processing circuitry to:
 analyze the audio data using a machine learning technique to detect and recognize a sound event, wherein to analyze the audio data includes to determine that the sound event represents a verbal call to an operator of the vehicle by a person outside of the vehicle; 
 in response to a successful recognition of the sound event from the audio data:
 determine, based on the analysis of the audio data, whether the verbal call relates to a safety condition; 
 in response to a determination that the verbal call relates to the safety condition, cause a vehicle control device to change a trajectory of the vehicle; and 
 cause the vehicle to emit a communication to the person outside of the vehicle; 
 
 in response to an unsuccessful recognition of the sound event from the audio data, identify or label the audio data as containing the sound event from a user input; and 
 in response to the audio data being labeled as containing the sound event, use the labeled audio data to identify a similar sound event in a subsequent classification; 
 
 a vehicle interface to:
 transmit a message to a vehicle control system, the message based on the sound event. 
 
 
     
     
       2. The system of  claim 1 , wherein in response to a successful recognition of the sound event from the audio data, the processing circuitry causes the audio processor to toggle off at least one microphone in the microphone array while the communication is emitted to the person outside of the vehicle, wherein the vehicle emits the communication to the person outside of the vehicle through the speaker, wherein the at least one microphone is toggled off while the communication is emitted to the person outside of the vehicle through the speaker, wherein the sound event represents a critical event, wherein when the sound event represents a critical event, the vehicle interface transmits a second message via a network to an external entity, and wherein the external entity is at least one of: a local law enforcement agency, an emergency roadside assistance service, an emergency health service, or an emergency contact. 
     
     
       3. The system of  claim 1 , wherein the machine learning technique comprises an artificial neural network. 
     
     
       4. The system of  claim 1 , wherein transmitting the message comprises transmitting the message using a Controller Area Network bus. 
     
     
       5. The system of  claim 1 , wherein the vehicle control system performs a responsive action based on the message. 
     
     
       6. The system of  claim 5 , wherein the responsive action comprises an autonomous vehicle maneuver. 
     
     
       7. The system of  claim 5 , wherein the responsive action comprises displaying an alert to an occupant of the vehicle. 
     
     
       8. The system of  claim 5 , wherein the responsive action comprises transmitting a distress call to an emergency response entity. 
     
     
       9. The system of  claim 5 , wherein the responsive action comprises initiating a person identification routine, the person identification routine to determine an identity of a person associated with the audio data. 
     
     
       10. The system of  claim 9 , wherein the audio processor is to cause the transmission of a directed audio signal to the person associated with the audio data. 
     
     
       11. A method for audio events detection in a vehicle, the method comprising:
 receiving audio data, the audio data sensed by a microphone array installed on the vehicle; 
 analyzing the audio data using a machine learning technique to recognize a sound event, wherein analyzing the data includes to determining that the sound event represents a verbal call to an operator of the vehicle by a person outside of the vehicle; 
 in response to a successful recognition of the sound event from the audio data:
 determining, based on analyzing the audio data, whether the verbal call relates to a safety condition; 
 in response to determining that the verbal call relates to the safety condition, causing a vehicle control device to change a trajectory of the vehicle; and 
 causing the vehicle to emit a communication to the person outside of the vehicle; 
 
 in response to an unsuccessful recognition of the sound event from the audio data in the audio data, identify or label the audio data as containing the sound event from a user input, and wherein, in response to the audio data being labeled as containing the sound event, the machine learning technique is updated with the labeled audio data to identify a similar sound event in a subsequent classification; and 
 transmitting a message to a vehicle control system, the message based on the sound event. 
 
     
     
       12. The method of  claim 11 , wherein at least one microphone in the microphone array is toggled off while the communication is emitted to the person outside of the vehicle, wherein the vehicle emits the communication to the person outside of the vehicle through a speaker installed on the vehicle, wherein the at least one microphone is toggled off while the communication is emitted to the person outside of the vehicle through the speaker, and wherein the machine learning technique comprises a support vector machine. 
     
     
       13. The method of  claim 11 , wherein transmitting the message comprises transmitting the message using a Controller Area Network bus. 
     
     
       14. The method of  claim 11 , wherein the vehicle control system performs a responsive action based on the message. 
     
     
       15. The method of  claim 14 , wherein the responsive action comprises an autonomous vehicle maneuver. 
     
     
       16. The method of  claim 14 , wherein the responsive action comprises displaying an alert to an occupant of the vehicle. 
     
     
       17. The method of  claim 14 , wherein the responsive action comprises transmitting a distress call to an emergency response entity. 
     
     
       18. The method of  claim 14 , wherein the responsive action comprises initiating a person identification routine, the person identification routine to determine an identity of a person associated with the audio data. 
     
     
       19. The method of  claim 18 , further comprising transmitting a directed audio signal to the person associated with the audio data. 
     
     
       20. At least one machine-readable medium including instructions for audio events detection in a vehicle, the instructions when executed by a machine, cause the machine to perform operations comprising:
 receiving audio data, the audio data sensed by a microphone array installed on the vehicle; 
 analyzing the audio data using a machine learning technique to recognize a sound event, wherein analyzing the data includes determining that the sound event represents a verbal call to an operator of the vehicle by a person outside of the vehicle; 
 in response to a successful recognition of the sound event from audio data:
 determining, based on analyzing the audio data, whether the verbal call relates to a safety condition; 
 in response to determining that the verbal call relates to the safety condition, causing a vehicle control device to change a trajectory of the vehicle; and 
 cause the vehicle to emit a communication to the person outside of the vehicle; 
 
 in response to an unsuccessful recognition of the sound event from audio data, identify or label the audio data as containing the sound event from a user input, and wherein, in response to the audio data being labeled as containing the sound event, the machine learning technique is updated with the labeled audio data to identify a similar sound event in a subsequent classification; and 
 transmitting a message to a vehicle control system, the message based on the sound event. 
 
     
     
       21. The at least one machine-readable medium of  claim 20 , wherein at least one microphone in the microphone array is toggled off while the communication is emitted to the person outside of the vehicle, wherein the vehicle emits the communication to the person outside of the vehicle through a speaker installed on the vehicle, wherein the at least one microphone is toggled off while the communication is emitted to the person outside of the vehicle through the speaker, wherein the sound event represents a critical event, wherein when the sound event represents a critical event, a vehicle interface transmits a second message via a network to an external entity, and wherein the external entity is at least one of: a local law enforcement agency, an emergency roadside assistance service, an emergency health service, or an emergency contact. 
     
     
       22. The at least one machine-readable medium of  claim 20 , wherein the vehicle control system performs a responsive action based on the message. 
     
     
       23. The at least one machine-readable medium of  claim 22 , wherein the responsive action comprises an autonomous vehicle maneuver.